@inproceedings{liao-etal-2024-pptser,
title = "{PPTSER}: A Plug-and-Play Tag-guided Method for Few-shot Semantic Entity Recognition on Visually-rich Documents",
author = "Liao, Wenhui and
Wang, Jiapeng and
Lin, Zening and
Xiong, Longfei and
Jin, Lianwen",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.626",
pages = "10522--10539",
abstract = "Visually-rich document information extraction (VIE) is a vital aspect of document understanding, wherein Semantic Entity Recognition (SER) plays a significant role. However, few-shot SER on visually-rich documents remains relatively unexplored despite its considerable potential for practical applications. To address this issue, we propose a simple yet effective Plug-and-Play Tag-guided method for few-shot Semantic Entity Recognition (PPTSER) on visually-rich documents. PPTSER is built upon off-the-shelf multi-modal pre-trained models. It leverages the semantics of the tags to guide the SER task, reformulating SER into entity typing and span detection, handling both tasks simultaneously via cross-attention. Experimental results illustrate that PPTSER outperforms existing fine-tuning and few-shot methods, especially in low-data regimes. With full training data, PPTSER achieves comparable or superior performance to fine-tuning baseline. For instance, on the FUNSD benchmark, our method improves the performance of LayoutLMv3-base in 1-shot, 3-shot and 5-shot scenarios by 15.61{\%}, 2.13{\%}, and 2.01{\%}, respectively. Overall, PPTSER demonstrates promising generalizability, effectiveness, and plug-and-play nature for few-shot SER on visually-rich documents. The codes will be available at [https://github.com/whlscut/PPTSER](https://github.com/whlscut/PPTSER).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liao-etal-2024-pptser">
<titleInfo>
<title>PPTSER: A Plug-and-Play Tag-guided Method for Few-shot Semantic Entity Recognition on Visually-rich Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenhui</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiapeng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zening</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Longfei</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lianwen</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Visually-rich document information extraction (VIE) is a vital aspect of document understanding, wherein Semantic Entity Recognition (SER) plays a significant role. However, few-shot SER on visually-rich documents remains relatively unexplored despite its considerable potential for practical applications. To address this issue, we propose a simple yet effective Plug-and-Play Tag-guided method for few-shot Semantic Entity Recognition (PPTSER) on visually-rich documents. PPTSER is built upon off-the-shelf multi-modal pre-trained models. It leverages the semantics of the tags to guide the SER task, reformulating SER into entity typing and span detection, handling both tasks simultaneously via cross-attention. Experimental results illustrate that PPTSER outperforms existing fine-tuning and few-shot methods, especially in low-data regimes. With full training data, PPTSER achieves comparable or superior performance to fine-tuning baseline. For instance, on the FUNSD benchmark, our method improves the performance of LayoutLMv3-base in 1-shot, 3-shot and 5-shot scenarios by 15.61%, 2.13%, and 2.01%, respectively. Overall, PPTSER demonstrates promising generalizability, effectiveness, and plug-and-play nature for few-shot SER on visually-rich documents. The codes will be available at [https://github.com/whlscut/PPTSER](https://github.com/whlscut/PPTSER).</abstract>
<identifier type="citekey">liao-etal-2024-pptser</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.626</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>10522</start>
<end>10539</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PPTSER: A Plug-and-Play Tag-guided Method for Few-shot Semantic Entity Recognition on Visually-rich Documents
%A Liao, Wenhui
%A Wang, Jiapeng
%A Lin, Zening
%A Xiong, Longfei
%A Jin, Lianwen
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F liao-etal-2024-pptser
%X Visually-rich document information extraction (VIE) is a vital aspect of document understanding, wherein Semantic Entity Recognition (SER) plays a significant role. However, few-shot SER on visually-rich documents remains relatively unexplored despite its considerable potential for practical applications. To address this issue, we propose a simple yet effective Plug-and-Play Tag-guided method for few-shot Semantic Entity Recognition (PPTSER) on visually-rich documents. PPTSER is built upon off-the-shelf multi-modal pre-trained models. It leverages the semantics of the tags to guide the SER task, reformulating SER into entity typing and span detection, handling both tasks simultaneously via cross-attention. Experimental results illustrate that PPTSER outperforms existing fine-tuning and few-shot methods, especially in low-data regimes. With full training data, PPTSER achieves comparable or superior performance to fine-tuning baseline. For instance, on the FUNSD benchmark, our method improves the performance of LayoutLMv3-base in 1-shot, 3-shot and 5-shot scenarios by 15.61%, 2.13%, and 2.01%, respectively. Overall, PPTSER demonstrates promising generalizability, effectiveness, and plug-and-play nature for few-shot SER on visually-rich documents. The codes will be available at [https://github.com/whlscut/PPTSER](https://github.com/whlscut/PPTSER).
%U https://aclanthology.org/2024.findings-acl.626
%P 10522-10539
Markdown (Informal)
[PPTSER: A Plug-and-Play Tag-guided Method for Few-shot Semantic Entity Recognition on Visually-rich Documents](https://aclanthology.org/2024.findings-acl.626) (Liao et al., Findings 2024)
ACL